phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-27 00:42:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: separate build and run provider types

Browse source 
in #2637, I combined the run and build config provider types to both use `Provider`

since this includes a provider_id, a user must now specify this when writing a build yaml. This is not very clear because all a user should care about upon build is the code to be installed (the module and the provider_type)

introduce `BuildProvider` and fixup the parts of the code impacted by this

Signed-off-by: Charlie Doern <cdoern@redhat.com>
This commit is contained in:
Charlie Doern 2025-07-25 14:34:06 -04:00
parent 025163d8e6
commit 236a670fc1
19 changed files with 401 additions and 754 deletions
Download patch file Download diff file Expand all files Collapse all files

33
llama_stack/templates/nvidia/build.yaml
View file

@ -3,37 +3,26 @@ distribution_spec:
description: Use NVIDIA NIM for running LLM inference, evaluation and safety
providers:
inference:
- provider_id: nvidia
provider_type: remote::nvidia
- provider_type: remote::nvidia
vector_io:
- provider_id: faiss
provider_type: inline::faiss
- provider_type: inline::faiss
safety:
- provider_id: nvidia
provider_type: remote::nvidia
- provider_type: remote::nvidia
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
- provider_type: inline::meta-reference
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
- provider_type: inline::meta-reference
eval:
- provider_id: nvidia
provider_type: remote::nvidia
- provider_type: remote::nvidia
post_training:
- provider_id: nvidia
provider_type: remote::nvidia
- provider_type: remote::nvidia
datasetio:
- provider_id: localfs
provider_type: inline::localfs
- provider_id: nvidia
provider_type: remote::nvidia
- provider_type: inline::localfs
- provider_type: remote::nvidia
scoring:
- provider_id: basic
provider_type: inline::basic
- provider_type: inline::basic
tool_runtime:
- provider_id: rag-runtime
provider_type: inline::rag-runtime
- provider_type: inline::rag-runtime
image_type: conda
image_name: nvidia
additional_pip_packages: